Step: g) How to make inference on images based on a trained model not working

[tejgvsl]

Hello Mr.Hu,
Step-g) How to make inference on images based on a trained model
Test on other images: (e.g. sample_inputs/a.png)
python2 fc4.py test pretrained/colorchecker_fold1and2.ckpt -1 sample_inputs/a.png

is not working with the above command. Observing the below error:

Loading image pack None
Traceback (most recent call last):
File "fc4.py", line 227, in
globals()mode
File "fc4.py", line 34, in test
data = load_data(image_pack_name.split(','))
File "/data/color_constancy/fc4/data_provider.py", line 23, in load_data
with open(fn) as f:
TypeError: coercing to Unicode: need string or buffer, NoneType found

Please help to resolve the issue. Tried to execute with sample_inputs/a.png

Thank you..

[yuanming-hu]

Thanks for letting me know. I'm travelling and will take a look once I get back to MIT.

[chiuhc]

It works fine in my environment.
You can try to use pdb.set_trace() to print out input filename and see if there is any weird thing occur under your environment, so that test_external() is not able to cv2.imread the image file correctly.

[tejgvsl]

Hi...
Finally able to run inference on own image using 'python3', with below change to resolve pickle load compatibility issue:
replace Line: 22 in squeeze_net.py -----> self.model = pkl.load(open(MODEL_PATH, 'r')) with

with open(MODEL_PATH, "rb") as f:
self.model = pkl.load(f, encoding="latin")

However the issue still remains with python2.
Please correct if i am missing something.

Thank you.
Tej.

[cploveflower]

Thank you for the providing,I have solved my question.